Abstract
Superresolution is an image processing technique for improving image quality and enhancing low-resolution images. This paper presents a novel interpolation method for increasing superresolution reconstruction effectiveness using a triangulation interpolation algorithm for automatic Thai sign language feature extraction. This approach uses three neighboring pixels for estimation. The experiment compared the superresolution reconstruction performance using the triangulation interpolation algorithm and the nearest-neighbor, SRCNN, bilinear, bicubic, GPR, and NEDI methods. The super-resolution reconstruction using the triangulation-improved interpolation technique provided the best PSNR measurements of image quality between the original and superresolution-reconstructed images. The PSNR value of the sign language image was 40.608, improving performance by 13.15%. The Thai sign language gesture recognition using 2D convolutional neural networks showed that the designed model increased the gesture recognition effectiveness with an accuracy of 0.95 and loss of 0.14. Thus, this study provides state-of-the-art superresolution reconstruction for automatic Thai sign language gesture recognition.
Highlights
Sign language is the communication way among people who are hearing impaired
This study proposed a new approach to reconstruct SR images using triangulation interpolation for training automatic Thai sign language (TSL) recognition
This study offered a novel approach to determine SR performance using a triangulation interpolation algorithm for recognizing distinct sign language features
Summary
Sign language is the communication way among people who are hearing impaired. On the other hand, most normal people cannot understand sign language and it’s a major problem to communicate between deaf and normal. In the last few years, this technique has been studied for various purposes, including remote detection, object detection, and recognition [2, 3] This technique has been applied to aerial photos, spatial images, satellite images [5], and medical applications such as Xray imaging. The SR reconstruction process can be classified as multi-frame and single-frame [2] Both reconstruction techniques improve and enhance original single images and scale and rotate to produce higher-resolution images. SR transforms multi-frame and single-frame LR images into HR images This technique resolves many issues related to remote sensing, robot vision, video enhancement, and medical imaging [21]. These processes enlarge the input to enhance the image resolution, increase the density, and reduce noise. These properties are essential for image fusion [22]
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
